Content Quality Evaluation and Classification

1. A computer-implemented method, comprising: receiving a request for a plurality of content items to be presented to a user of a social networking system, the user connected to a plurality of other users in the social networking system; for each of a set of candidate content items for the user: identifying one or more features of the candidate content item, the one or more features related to a quality of the candidate content item, determining one or more classifiers based on the one or more features identified, the one or more classifiers describing the quality of the candidate content item, and computing a quality metric for the candidate content item based on the one or more classifiers, the quality metric indicating the quality of the candidate content item relative to other candidate content items of the set and indicating a likelihood that the candidate content item is junk or spam; and providing the computed quality metric for each of the candidate content items of the set to a content item ranking process to select the plurality of content items to present to the user.

2. The computer-implemented method of claim 1 , further comprising: accessing the set of candidate content items for the user in response to the request, each of the candidate content items having an initial ranking for the user relative to other candidate content items that affects whether the candidate content item is selected for presentation to the user, wherein providing the computed quality metric for each of the candidate content items of the set to the content item ranking process further comprises adjusting the initial ranking of each of the candidate content items to account for the quality of the content items according to the quality metric for each of the candidate content items of the set.

3. The computer-implemented method of claim 2 , further comprising: selecting from the set of candidate content items the plurality of content items to present to the user in a newsfeed based on the adjusted rankings of the candidate content items.

4. The computer-implemented method of claim 1 , wherein providing the computed quality metric for each of the candidate content item of the set to the content item ranking process further comprises including the computed quality metric as one of multiple inputs into the content item ranking process for ranking the candidate content items and selecting from the ranked candidate content items the plurality of content items to present to the user in a newsfeed.

5. The computer-implemented method of claim 1 , wherein the one or more classifiers comprise classifiers for the candidate content item based on originality of the candidate content item, gaming nature of the candidate content item, engagement of other users with the candidate content item, a quality of a hyperlink in the candidate content item, or an owner of the candidate content item.

6. The computer-implemented method of claim 1 , wherein identifying one or more features of the candidate content item comprises determining originality of the candidate content item, the determination comprising comparing a fingerprint of content of the candidate content item to fingerprints of content of previously posted content items in the social networking system, wherein a match with one of the fingerprints of content of previously posted content items indicates that the content of the candidate content item exists in the social networking system.

7. The computer-implemented method of claim 6 , wherein a classifier of the one or more classifiers is determined based on a number of instances the content of the candidate content item found in the social networking system, and wherein the quality metric is applied in the content item ranking process to decrease a ranking of the candidate content item relative to other candidate content items of the set.

8. The computer-implemented method of claim 1 , wherein identifying one or more features of the candidate content item comprises evaluating whether the content of the candidate content item solicits interest from the user.

9. The computer-implemented method of claim 8 , wherein a classifier of the one or more classifiers is determined based on an explicitness with which the content item solicits interest, and wherein the quality metric is applied in the content item ranking process to assign less credit to each interest in the candidate content item than otherwise would be given.

10. The computer-implemented method of claim 2 , wherein identifying one or more features of the candidate content item comprises identifying features relating to a quality of engagement of other users with the content item based on a number of shares of or comments on the candidate content item, whether the candidate content item included a message with a share of the candidate content item, an average length of a message included with a share or in a comment on the candidate content item, or an average length of comments on the candidate content item, or an affinity of users who interacted with the candidate content item for a user who posted the content candidate content item.

11. The computer-implemented method of claim 2 , wherein identifying one or more features of the candidate content item comprises identifying features relating to a link quality of a hyperlink included in the candidate content item based on a ratio of clicks on or selections of the hyperlink by users to indications of interest or likes of the hyperlink by users, a higher ratio indicating a lower link quality, and wherein the quality metric is computed such that the candidate content item receives less credit in the content item ranking process than otherwise would be for clicks on or selections of the hyperlink.

12. The computer-implemented method of claim 2 , wherein identifying one or more features of the candidate content item comprises accessing a label applied to a page that posted the candidate content item, the label indicating a quality of the page, and wherein the quality of the page is included in the quality metric for the quality of the candidate content item posted by that page.

13. A computer program product comprising a non-transitory computer-readable storage medium containing computer program code for: receiving a request for a plurality of content items to be presented to a user of a social networking system, the user connected to a plurality of other users in the social networking system; for each of a set of candidate content items for the user: identifying one or more features of the candidate content item, the one or more features related to a quality of the candidate content item, determining one or more classifiers based on the one or more features identified, the one or more classifiers describing the quality of the candidate content item, and computing a quality metric for the candidate content item based on the one or more classifiers, the quality metric indicating the quality of the candidate content item relative to other candidate content items of the set and indicating a likelihood that the candidate content item is junk or spam; and providing the computed quality metric for each of the candidate content items of the set to a content item ranking process to select the plurality of content items to present to the user.

14. The computer program product of claim 13 , where the computer-readable storage medium further contains computer program code for: accessing the set of candidate content items for the user in response to the request, each of the candidate content items having an initial ranking for the user relative to other candidate content items that affects whether the candidate content item is selected for presentation to the user, wherein providing the computed quality metric for each of the candidate content items of the set to the content item ranking process further comprises adjusting the initial ranking of each of the candidate content items to account for the quality of the content items according to the quality metric for each of the candidate content items of the set.

15. The computer program product of claim 14 , where the computer-readable storage medium further contains computer program code for: selecting from the set of candidate content items the plurality of content items to present to the user in a newsfeed based on the adjusted rankings of the candidate content items.

16. The computer program product of claim 13 , wherein providing the computed quality metric for each of the candidate content item of the set to the content item ranking process further comprises including the computed quality metric as one of multiple inputs into the content item ranking process for ranking the candidate content items and selecting from the ranked candidate content items the plurality of content items to present to the user in a newsfeed.

17. The computer program product of claim 13 , wherein the one or more classifiers comprise classifiers for the candidate content item based on originality of the candidate content item, gaming nature of the candidate content item, engagement of other users with the candidate content item, a quality of a hyperlink in the candidate content item, or an owner of the candidate content item.

18. The computer program product of claim 13 , wherein identifying one or more features of the candidate content item comprises determining originality of the candidate content item, the determination comprising comparing a fingerprint of content of the candidate content item to fingerprints of content of previously posted content items in the social networking system, wherein a match with one of the fingerprints of content of previously posted content items indicates that the content of the candidate content item exists in the social networking system.

19. The computer program product of claim 18 , wherein a classifier of the one or more classifiers is determined based on a number of instances the content of the candidate content item found in the social networking system, and wherein the quality metric is applied in the content item ranking process to decrease a ranking of the candidate content item relative to other candidate content items of the set.

20. The computer program product of claim 13 , wherein identifying one or more features of the candidate content item comprises identifying features indicating a gaming nature of the candidate content item based on an evaluation of content included in the candidate content item for a solicitation from the user for interest in the candidate content item.

21. The computer program product of claim 13 , wherein the quality metric is computed such that each interest in the candidate content item receives less credit in the content item ranking process than otherwise would be given.

22. The computer program product of claim 13 , wherein identifying one or more features of the candidate content item comprises identifying features relating to a quality of engagement of other users with the content item based on a number of shares of or comments on the candidate content item, whether the candidate content item included a message with a share of the candidate content item, an average length of a message included with a share or in a comment on the candidate content item, or an average length of comments on the candidate content item, or an affinity of users who interacted with the candidate content item for a user who posted the content candidate content item.

23. The computer program product of claim 13 , wherein identifying one or more features of the candidate content item comprises identifying features relating to a link quality of a hyperlink included in the candidate content item based on a ratio of clicks on or selections of the hyperlink by users to indications of interest or likes of the hyperlink by users, a higher ratio indicating a lower link quality, and wherein the quality metric is computed such that the candidate content item receives less credit in the content item ranking process than otherwise would be for clicks on or selections of the hyperlink.

24. The computer program product of claim 13 , wherein identifying one or more features of the candidate content item comprises accessing a label applied to a page that posted the candidate content item, the label indicating a quality of the page, and wherein the quality of the page is included in the quality metric for the quality of the candidate content item posted by that page.